Ordered Logit Regression Modeling of the Self- Rated Health in Hawai i, With Comparisons to the OLS Model
|
|
- Kristian Lamb
- 5 years ago
- Views:
Transcription
1 Journal of Modern Applied Statistical Methods Volume 12 Issue 2 Article Ordered Logit Regression Modeling of the Self- Rated Health in Hawai i, With Comparisons to the OLS Model Hosik Min University of South Alabama, Mobile, AL, hksmin@gmail.com Follow this and additional works at: Part of the Applied Statistics Commons, Social and Behavioral Sciences Commons, and the Statistical Theory Commons Recommended Citation Min, Hosik (2013) "Ordered Logit Regression Modeling of the Self-Rated Health in Hawai i, With Comparisons to the OLS Model," Journal of Modern Applied Statistical Methods: Vol. 12 : Iss. 2, Article 23. DOI: /jmasm/ Available at: This Regular Article is brought to you for free and open access by the Open Access Journals at DigitalCommons@WayneState. It has been accepted for inclusion in Journal of Modern Applied Statistical Methods by an authorized editor of DigitalCommons@WayneState.
2 Journal of Modern Applied Statistical Methods November 2013, Vol. 12, No. 2, Copyright 2013 JMASM, Inc. ISSN Ordered Logit Regression Modeling of the Self-Rated Health in Hawai i, With Comparisons to the OLS Model Hosik Min University of South Alabama Mobile, AL Despite the ordinal nature of Self-Rated Health (SRH) variable, logistic regression models or regression models have been used without adequate justification for these applications. It is shown that ordered-logit regression model is the appropriate statistical strategy to estimate SRH, whereas the Ordinary LeastSquares model leads to biased conclusions. Keywords: status Ordered logit regression, OLS, ordinal outcome, self-rated health, health Introduction Self-Rated Health (SRH) has long been a major research topic in health-related research (Mossey & Shapiro, 1982; Idler & Angel, 1990; Miilunpalo, Vuori, Oja, Pasanen, & Urponen, 1997; Eriksson, Unden, & Elofsson, 2001). The main reasons for this are that SRH can be used as an individual s general health status and/or an indicator of his or her quality of life and that the research importance of SRH will continue to increase because of a growing interest in health and healthy living (McMurdo, 2000; Eriksson, Unden, & Elofsson, 2001). Given the increased life expectancy and the aging of the population (NCHS, 2007), suffering and death from various diseases have declined, while the topic of healthy living has received greater attention (Row & Kahn, 1987; Glasgow, 2004; Glasgow, Min, & Brown, 2013). Health or lack thereof includes not only physical factors such as limitations to daily life activities (ADL) but also mental indicators such as SRH. As health condition and/or status can impact an individual s well-being in positive or negative ways, it is an important topic in public health. Dr. Min is assistant professor in the Department of Sociology, Anthropology, and Social Work. him at: hksmin@gmail.com 371
3 ORDERED LOGIT REGRESSION MODELING Here the focus will be on methodological aspects; that is, the appropriateness of the ordered logit model for SRH, by comparing the results obtained using this method with those from the OLS model. SRH has often been measured as an ordinal variable; for instance, it is measured as a 5-point scale in this study (1=Poor, 2=Fair, 3=Good, 4=Very Good, and 5=Excellent). The analytical approach to handling this type of variable, however, is often logit regression (Avanath & Kleinbaum, 1997; Manor, Matthew, & Power, 2000; Pohlmann & Leitner, 2003) or Ordinary Least Squares (OLS) model (Winship & Mare, 1984; Wardle & Steptoe, 2003). The use of logit regression model can be easily denied because the logit model cannot deal with a dependent variable with more than two categorical and ordered outcomes in an appropriate way. In other words, if the SRH is developed as a dichotomous variable e.g., poor versus good and then a logit model is employed to estimate the logit coefficients, the results would lead to the loss of important information about the dependent variable (Hamilton, 1992; Berry, 1993; Hamilton, 1995; Avanath & Kleinbaum, 1997; Pohlmann & Leitner, 2003). In addition, only small percentage of Hawai i adults were having poor SRH (only 3%) in this study. Moreover, other kinds of social, cultural, and socioeconomic factors differentiating people who have good, very good, and excellent SRH will not be estimated if we use logit model. Therefore, the goals of this paper are to present the methodological problems by comparing OLS, which often used to estimate ordinal outcome, and ordered logit models and to offer an easily understandable comparison of two methods by examining the likelihood of having a higher SRH in Hawai i. Considering wide use of OLS model for the dependent variable with many categories in ordered measurement (Mekelvey & Zavonia, 1975; Avanath & Kleinbaum, 1997), examining the statistical assumptions and violations the OLS model causes with ordered logit model would provide us a meaningful insights for employing an appropriate statistical methodology. In addition, this is a particularly important and relevant concern, given the expected increase in interest in general health status, both physical and mental. As was indicated (Hawkes, 1971; Reynolds, 1973; Mekelvey & Zavonia, 1975; O Brien, 1982), analyzing an ordinal variable with an ordinal regression model could lead to incorrect conclusions by violating the assumptions of the ordinal regression model. The OLS model has several assumptions known as a best linear unbiased estimating method (BLUE) (Hamilton, 1992; Berry, 1993; Hamilton, 1995; Avanath & Kleinbaum, 1997; Menard, 2001). For instance, the OLS model expects the dependent variable as linear and continuous one; the OLS model assumes that the mean of errors of prediction in the population regression 372
4 HOSIK MIN function must be zero; and the variance of the error term is constant for all values of independent variables, homoscedasticity If the dependent variable is ordinal, however, these assumptions in general are not met (Mekelvey & Zavonia, 1975; Fox, 1991; Hamilton, 1992; Berry, 1993; Hamilton, 1995; Avanath & Kleinbaum, 1997). First of all, the ordinal dependent variable is non-linear, the values are presented in 0 to 1 probability as in a logit regression model; a non-linear model must have a different error structure and the error term does not have constant variance. As McKelvey and Zavoina (1975) argued, the OLS model may, in some cases, have the undesirable effect of causing regression analysis to severely underestimate the relative impact of certain variables. Accordingly, the ordered logit model, instead OLS model is considered to be the most appropriate methods if the dependent variable is ordinal to estimate more accurately (Hawkes, 1971; Reynolds, 1973; Mekelvey & Zavonia, 1975; O Brien, 1982; Avanath & Kleinbaum, 1997; Pohlmann & Leitner, 2003). Consequently, the best-fitting and most appropriate statistical model for handling the ordinal outcome is an ordered or probit model. This study, however, will use and focus on an ordered logit model, because the results of these two methods are similar and the ordered logit model is more common and its results are easier to interpret (Long & Freese, 2003). Data and Methods As described above, to measure the overall assessment of respondents health, self-rated health (SRH) is used as a dependent variable. SRH is measured by a five-point scale and thus has a categorical and ordered nature. The best-fitting statistical model for handling the ordered outcome is known as an ordered-logistic regression model, which will be used as an analytical model here. Here is an explanation of the ordered logit regression model. For the sake of explanation, symbols rather than actual variable names will be used (Long & Freese, 2003). Posit that Y is an ordinal dependent variable with c categories, and Pr ( Y j) denotes the probability that the response on Y falls in category j or below (i.e., in category 1, 2,, or j). This is called a cumulative probability. It equals the sum of the probabilities in category j and below: ( Y j) ( Y ) ( ( Y ) ( Y j) Pr = Pr = 1 + Pr = Pr = (1) 373
5 ORDERED LOGIT REGRESSION MODELING A c-category Y-dependent variable has c cumulative probabilities: Pr 1 Pr 2 Pr Y c. The final cumulative probability uses the ( Y ), ( Y ),, ( ) entire scale; as a consequence, therefore, ( Y c) Pr = 1. The order of forming the final cumulative probabilities reflects the ordering of the dependent variable scale, and those probabilities themselves satisfy: ( Y ) ( Y ) ( Y c) Pr 1 Pr 2... Pr = 1 (2) In an ordered logit model, an underlying probability score for an observation of being in the i th response category is estimated as a linear function of the independent variables and a set of cut points. The probability of observing response category i corresponds to the probability that the estimated linear function, plus random error, is within the range of the cut points estimated for that response. th ( i) ( ki 1 < bx 1 1j + bx 2 2 j + + bk Xkj + uj ki ) Pr Response Category for the j Outcome = = Pr... (3) It is necessary to estimate the coefficients b 1, b 2,...,b k along with cut points k1, k2,...,k i 1 where i is the number of possible response categories of the dependent variable. The coefficients and cut points are estimated using maximum likelihood. To do this, the data used in this paper were obtained from the 2005 Hawaii Health Survey (HHS). The HHS is a representative-sample survey based on household, administered as a telephone interview survey to adult residents in more than 6,000 households each year. The principle objective of the survey is to provide statewide estimates of population parameters that describe (1) the current health status of the population; (2) respondents access to and utilization of health care; and (3) the distribution of the population by age, sex, and ethnicity (SMS Research & Marketing Services, Inc., 2006). The ordered logit regression model is thus estimated for the Hawai i residents that predict their SRH using other socio-demographic and locale characteristics that have been shown in the demographic literature to be associated with SRH (Mossey & Shapiro, 1982; Idler & Angel, 1990; Kennedy, Kawachi, Glass, & Prothrow-Stith, 1998; Kawachi, Kennedy, & Glass, 1999; 374
6 HOSIK MIN Eriksson, Unden, & Elofsson, 2001). The controlling variables pertain to age, sex, race/ethnicity, marital status, education, and residential location. Some are measured as dummy variables and others as interval. The variables are as follows: 1) Age is measured in years from age 18 to 99; 2) Male is a dummy variable indicating whether the respondent is male; if yes, it is coded as 1; 3) Married is a dummy variable indicating whether s/he is married; if yes, it is coded as 1; 4) Hawaiian is a dummy variable indicating whether the respondent is Native Hawaiian; if yes, it is coded as 1; 5) Japanese is a dummy variable indicating whether s/he is Japanese American; if yes, it is coded as 1; 6) Filipino is a dummy variable indicating whether the respondent is Filipino American; if yes, it is coded as 1; and 7) Other is a dummy variable indicating whether s/he belongs to Other ethnic categories; if yes, it is coded as 1 (with White used as the reference group); 8) Education is measured as 6 categories from illiterate to 4 or more years of college education (1=Illiterate/Only Kindergarten; 2=Grade 1 to 8; 3=Grade 9-11; 4=Grade 12 or GED; 5=College, 1 to 3 years; 6=College, 4 years or more); 9) Big Island is a dummy variable indicating whether the respondent lives in Big Island; if yes, it is coded as 1; 10) Kaua i is a dummy variable indicating whether s/he lives in Kaua i; if yes, it is coded as 1; 11) Maui is a dummy variable indicating whether the respondent lives in Maui; if yes, it is coded as 1 (with O ahu used as reference variable). Results of Ordered Logit Regression Versus OLS Analysis Table 1 presents frequency distributions for all independent variables as well as the dependent one. The average score of SRH for Hawai i residents was 3.57, which lies between good and very good. The average age was 47.6 years old among the adult population (age 18 and over). Half of them were male (49%). Six out of ten Hawai i adults were married (60%). As for race/ethnicity, 21% were Native Hawaiian, 22% were Japanese American, 15% were Filipino, and 17% were Other. The average level of education was 4.86, or close to 1-3 years of college education. As for residence, 13% lived in Big Island, 5% lived in Kaua i, 12% lived in Maui, and the remaining 70% lived in O ahu. Table 2 presents the results of the ordered-logistic regression and the OLS analysis for Hawai i adults in The results show that overall model fit was significant for both models, and most coefficients in both models were significant. The older the respondent, the lower the SRH; if s/he was married, s/he was more likely to have a higher SRH; compared to white respondents, all other racial and 375
7 ORDERED LOGIT REGRESSION MODELING ethnic categories, such as Native Hawaiian, Japanese American, Filipino American, and Other, show a lower likelihood of having a higher SRH. Also, as expected, the more educated the respondent, the higher the SRH; a person living in Kaua i and Maui has a higher likelihood of having higher SRH compared to a person living in O ahu. Table 1. Descriptive Statistics from the 2005 Hawaii Health Survey (n=898, 593, weighted) Variable Mean Std. Dev. Self-rated Health Age Male Marital Status Married Race/Ethnicity Hawaiian Filipino Japanese Other Socioeconomic Status Education Residence Island Big Island Kaua i Maui The results, however, indeed present the evidence of inappropriateness of using OLS model compared to the ordered logit model. The male variable provided important information regardless of whether an ordered logit model or OLS was used to deal with an ordinal dependent variable. A male was shown to have a higher likelihood of having a higher SRH compared to female counterparts in the ordered logit regression model, but not in the OLS. As previous studies have pointed out, using an OLS model for an ordinal-dependent variable indeed produces this inconsistent and biased result: It could be concluded that male did 376
8 HOSIK MIN not have any effect on SRH, which would be crucially misleading in the OLS model. In addition, all the values of the coefficients in the OLS model were severely underestimated compared to those of the ordered logit model, which lessened the effects of contributing factors on SRH. Table 2. Comparison of the Analysis Results of Ordered Logit Regression and OLS from 2005 Hawaii Health Survey (n=898, 593, weighted) Ordered Logit Regression OLS Variable b z b t Age * * Male ** Marital Status Married * * Race/Ethnicity Hawaiian * * Japanese * * Filipino * * Other * * Socioeconomic Status Education * * Residence Island Big Island Kaua i 3.71 * * Maui * * LR Chi 2 106, F 10, Pseudo-R * Adj. R * * p<.05; ** p<.001 Note: The values of cut points to ordered logit regression and the value of constants for OLS are not shown here. 377
9 ORDERED LOGIT REGRESSION MODELING Discussion This paper deals with an appropriate use of statistical modeling that frequently occurs when modeling ordinal variables, Self-Rated Health, which is measured using a 5-point scale here. By comparing the results of ordered logit regression and OLS models, this study could illustrate the potential problems with using OLS in the analysis of ordinal SRH variables. While most of the conclusions from the OLS model were similar to those from the ordered logit regression model, significant differences do exist. Most of all, the insignificance of male in the OLS model could lead to incorrect conclusions regarding this variable. In fact, the significant and positive effect for male had on a respondent s SRH score was revealed when this study used the ordered logit model. Furthermore, the OLS model underestimated the effects of all coefficients. Accordingly, this study appears to show that the use of an ordered logit regression model is statistically appropriate for the modeling of Self-Rated Heath, which has an ordinal characteristic, in Hawai i s adult population. More specifically, the use of the ordered logit regression model could help avoid inconsistent and biased conclusions and their detrimental effects on public health policy. Considering the fact that the importance of studying health status indicators such as SRH continues to rise, the use of an appropriate analytical strategy will be invaluable in the future. References Avanath, C. V., & Kleinbaum, D. G. (1997). Regression models for ordinal responses: A review of methods and applications. International Journal of Epidemiology, 26, Berry, W. (1993). Understanding regression assumptions. 1 st ed. Sage Publications, Inc. Eriksson, I., Unden, A., & Elofsson, S. (2001). Self-rated health. Comparisons between three different measures. Results from a population study. International Journal of Epidemiology, 30, Fox, J. (1991). Regression diagnostics: an introduction. 1 st ed. Sage Publications, Inc. 378
10 HOSIK MIN Glasgow, N. (2004). Healthy aging in rural America. In (L. W. M. N. Glasgow, N. E. Johnson, Eds.) Critical issues in rural health (pp ). Ames, Iowa: Blackwell Publishing Professional. Glasgow, N., Min, H., & Brown, D. (2013). Volunteerism of older inmigrants and long-term residents in rural retirement destinations. In N. Glasgow & E. H. Berry (Ed.), Rural aging in 21 st century America (pp ). New York: Springer Publishing Company. Hamilton, L. C. (1992). Regression with graphics: A second course in applied statistics. 1 st ed. Cengage Learning. Hamilton, L. C. (1995). Data analysis for social scientists. 1 st ed. Boston, MA: Duxbury Press. Hawkes, R. K. (1971). The multivariate analysis of ordinal measures. The American Journal of Sociology, 76(5), Idler, E. L. & Angel, R. J. (1990). Self-rated health and mortality in the NHANES-1 epidemiologic follow-up study. American Journal of Public Health, 80, Kawachi, I., Kennedy, B. P., & Glass, R. (1999). Social capital and selfrated health: A contextual analysis. American Journal of Public Health, 89(8), Kennedy, B. P., Kawachi, I., Glass, R., & Prothrow-Stith, D. (1998). Income distribution, socioeconomic status, and self rated health in the United States: Multilevel analysis. BMJ: British Medical Journal, 317, Long, S. J., & Freese, J. (2003). Regression models for categorical dependent variables using STATA. A Stata Press Publication. STATA Corporation. College Station: TX. Manor, O., Matthew, S., & Power, C. (2000). Dichotomous or categorical response? Analysing self-rated health and lifetime social class. International Journal of Epidemiology, 29, Mckelvey, R. D., & Zavoina, W. (1975). A statistical model for the analysis of ordinal level dependent variables. Journal of Mathematical Sociology, 4, McMurdo, M. E. T. (2000). A healthy old age: Realistic or futile goal? BMJ: British Medical Journal, 321, Menard, S. (2001). Applied logistic regression analysis. 2 nd ed. Sage Publications, Inc. 379
11 ORDERED LOGIT REGRESSION MODELING Miilunpalo, S., Vuori, I., Oja, P., Pasanen, M., & Urponen, H. (1997). Selfrated health status as a health measure: The predictive value of self-reported health status on the use of physician services and on mortality in the working-age population. Journal of Clinical Epidemiology, 50(5), Mossey, J. M., & Shapiro, E. (1982). Self-rated health: A predictor of mortality among the elderly. American Joumal of Public Health, 72, National Center for Health Statistics. (2007). Health, United States, 2007 with chartbook on trends in the health of Americans. Hyattsville, MD. O'Brien, R.M. (1982). Using rank-order measures to represent continuous variables. Social Forces, 61, Pohlmann, J. T., & Leitner, W.W. (2003). A comparison of ordinary least squares and logisitc regression. Ohio Journal of Science, 103(5), Reynolds, H. T. (1973). On "the multivariate analysis of ordinal measures". American Journal of Sociology, 78(6), Row, J. W., & Kahn, R. L. (1987). Human aging: Usual and successful. Science, 273, SMS Research & Marketing Services, Inc. (2006). HHS update: Hawaii department of health, office of health status monitoring. Hawaii Health Survey, 2004, Procedure Manual. Honolulu, HI. Wardle, J., & Steptoe, A. (2003). Socioeconomic differences in attitudes and beliefs about healthy lifestyles. Journal of Epidemiology & Community Health, 57, Winship, C., & Mare, R. D. (1984). Regression models with ordinal variables. American Sociological Review, 49,
Changes in Stock Ownership by Race/Hispanic Status,
Consumer Interests Annual Volume 53, 2007 Changes in Stock Ownership by Race/Hispanic Status, 1998-2004 In 2004, 57% of White households directly and/or indirectly owned stocks, compared to less than 26%
More informationMinistry of Health, Labour and Welfare Statistics and Information Department
Special Report on the Longitudinal Survey of Newborns in the 21st Century and the Longitudinal Survey of Adults in the 21st Century: Ten-Year Follow-up, 2001 2011 Ministry of Health, Labour and Welfare
More informationFinal Exam - section 1. Thursday, December hours, 30 minutes
Econometrics, ECON312 San Francisco State University Michael Bar Fall 2013 Final Exam - section 1 Thursday, December 19 1 hours, 30 minutes Name: Instructions 1. This is closed book, closed notes exam.
More informationRacial/Ethnic Disparities Related to Health Insurance Coverage, Access to Care and Ease in Health Care Services among Children in 2012 CCHAPS Data
118 Racial/Ethnic Disparities Related to Health Insurance Coverage, Access to Care and Ease in Journal of Health Disparities Research and Practice Volume 8, Issue 1, Spring 2015, pp. 118-127 2011 Center
More informationBayesian Inference for Volatility of Stock Prices
Journal of Modern Applied Statistical Methods Volume 3 Issue Article 9-04 Bayesian Inference for Volatility of Stock Prices Juliet G. D'Cunha Mangalore University, Mangalagangorthri, Karnataka, India,
More informationLecture 07: Measures of central tendency
Lecture 07: Measures of central tendency Ernesto F. L. Amaral September 21, 2017 Advanced Methods of Social Research (SOCI 420) Source: Healey, Joseph F. 2015. Statistics: A Tool for Social Research. Stamford:
More informationThe Risk Tolerance and Stock Ownership of Business Owning Households
The Risk Tolerance and Stock Ownership of Business Owning Households Cong Wang and Sherman D. Hanna Data from the 1992-2004 Survey of Consumer Finances were used to examine the risk tolerance and stock
More informationModeling wages of females in the UK
International Journal of Business and Social Science Vol. 2 No. 11 [Special Issue - June 2011] Modeling wages of females in the UK Saadia Irfan NUST Business School National University of Sciences and
More informationFinancial Risk Tolerance and the influence of Socio-demographic Characteristics of Retail Investors
Financial Risk Tolerance and the influence of Socio-demographic Characteristics of Retail Investors * Ms. R. Suyam Praba Abstract Risk is inevitable in human life. Every investor takes considerable amount
More informationEconometric Methods for Valuation Analysis
Econometric Methods for Valuation Analysis Margarita Genius Dept of Economics M. Genius (Univ. of Crete) Econometric Methods for Valuation Analysis Cagliari, 2017 1 / 25 Outline We will consider econometric
More informationCOMMUNITY ADVANTAGE PANEL SURVEY: DATA COLLECTION UPDATE AND ANALYSIS OF PANEL ATTRITION
COMMUNITY ADVANTAGE PANEL SURVEY: DATA COLLECTION UPDATE AND ANALYSIS OF PANEL ATTRITION Technical Report: February 2012 By Sarah Riley HongYu Ru Mark Lindblad Roberto Quercia Center for Community Capital
More informationModule 9: Single-level and Multilevel Models for Ordinal Responses. Stata Practical 1
Module 9: Single-level and Multilevel Models for Ordinal Responses Pre-requisites Modules 5, 6 and 7 Stata Practical 1 George Leckie, Tim Morris & Fiona Steele Centre for Multilevel Modelling If you find
More informationCOMMUNITY ADVANTAGE PANEL SURVEY: DATA COLLECTION UPDATE AND ANALYSIS OF PANEL ATTRITION
COMMUNITY ADVANTAGE PANEL SURVEY: DATA COLLECTION UPDATE AND ANALYSIS OF PANEL ATTRITION Technical Report: March 2011 By Sarah Riley HongYu Ru Mark Lindblad Roberto Quercia Center for Community Capital
More informationRescaling results of nonlinear probability models to compare regression coefficients or variance components across hierarchically nested models
Rescaling results of nonlinear probability models to compare regression coefficients or variance components across hierarchically nested models Dirk Enzmann & Ulrich Kohler University of Hamburg, dirk.enzmann@uni-hamburg.de
More informationGetting Started in Logit and Ordered Logit Regression (ver. 3.1 beta)
Getting Started in Logit and Ordered Logit Regression (ver. 3. beta Oscar Torres-Reyna Data Consultant otorres@princeton.edu http://dss.princeton.edu/training/ Logit model Use logit models whenever your
More informationCategorical Outcomes. Statistical Modelling in Stata: Categorical Outcomes. R by C Table: Example. Nominal Outcomes. Mark Lunt.
Categorical Outcomes Statistical Modelling in Stata: Categorical Outcomes Mark Lunt Arthritis Research UK Epidemiology Unit University of Manchester Nominal Ordinal 28/11/2017 R by C Table: Example Categorical,
More informationsociology SO5032 Quantitative Research Methods Brendan Halpin, Sociology, University of Limerick Spring 2018 SO5032 Quantitative Research Methods
1 SO5032 Quantitative Research Methods Brendan Halpin, Sociology, University of Limerick Spring 2018 Lecture 10: Multinomial regression baseline category extension of binary What if we have multiple possible
More informationGetting Started in Logit and Ordered Logit Regression (ver. 3.1 beta)
Getting Started in Logit and Ordered Logit Regression (ver. 3. beta Oscar Torres-Reyna Data Consultant otorres@princeton.edu http://dss.princeton.edu/training/ Logit model Use logit models whenever your
More informationModel fit assessment via marginal model plots
The Stata Journal (2010) 10, Number 2, pp. 215 225 Model fit assessment via marginal model plots Charles Lindsey Texas A & M University Department of Statistics College Station, TX lindseyc@stat.tamu.edu
More informationUsing New SAS 9.4 Features for Cumulative Logit Models with Partial Proportional Odds Paul J. Hilliard, Educational Testing Service (ETS)
Using New SAS 9.4 Features for Cumulative Logit Models with Partial Proportional Odds Using New SAS 9.4 Features for Cumulative Logit Models with Partial Proportional Odds INTRODUCTION Multicategory Logit
More informationCOMMUNITY ADVANTAGE PANEL SURVEY: DATA COLLECTION UPDATE AND ANALYSIS OF PANEL ATTRITION
COMMUNITY ADVANTAGE PANEL SURVEY: DATA COLLECTION UPDATE AND ANALYSIS OF PANEL ATTRITION Technical Report: February 2013 By Sarah Riley Qing Feng Mark Lindblad Roberto Quercia Center for Community Capital
More informationEstimating Heterogeneous Choice Models with Stata
Estimating Heterogeneous Choice Models with Stata Richard Williams Notre Dame Sociology rwilliam@nd.edu West Coast Stata Users Group Meetings October 25, 2007 Overview When a binary or ordinal regression
More informationA STUDY ON FACTORS INFLUENCING OF WOMEN POLICYHOLDER S INVESTMENT DECISION TOWARDS LIFE INSURANCE CORPORATION OF INDIA POLICIES IN CHENNAI
www.singaporeanjbem.com A STUDY ON FACTORS INFLUENCING OF WOMEN POLICYHOLDER S INVESTMENT DECISION TOWARDS LIFE INSURANCE CORPORATION OF INDIA POLICIES IN CHENNAI Ms. S. Pradeepa, (PhD) Research scholar,
More informationMarital Disruption and the Risk of Loosing Health Insurance Coverage. Extended Abstract. James B. Kirby. Agency for Healthcare Research and Quality
Marital Disruption and the Risk of Loosing Health Insurance Coverage Extended Abstract James B. Kirby Agency for Healthcare Research and Quality jkirby@ahrq.gov Health insurance coverage in the United
More informationRetirees perceptions of quality of life
Available Online at http://iassr.org/journal 201 (c) EJRE published by International Association of Social Science Research - IASSR ISSN: 217-628 European Journal of Research on Education, 201, 2(Special
More informationA Microeconometric Analysis of Household Consumption Expenditure Determinants for Both Rural and Urban Areas in Turkey
American International Journal of Contemporary Research Vol. 2 No. 2; February 2012 A Microeconometric Analysis of Household Consumption Expenditure Determinants for Both Rural and Urban Areas in Turkey
More informationGrouped Data Probability Model for Shrimp Consumption in the Southern United States
Volume 48, Issue 1 Grouped Data Probability Model for Shrimp Consumption in the Southern United States Ferdinand F. Wirth a and Kathy J. Davis a Associate Professor, Department of Food Marketing, Erivan
More informationMortality Rates Estimation Using Whittaker-Henderson Graduation Technique
MATIMYÁS MATEMATIKA Journal of the Mathematical Society of the Philippines ISSN 0115-6926 Vol. 39 Special Issue (2016) pp. 7-16 Mortality Rates Estimation Using Whittaker-Henderson Graduation Technique
More informationCitation 長崎大学東南アジア研究年報. vol.45, p.13-20; 200
NAOSITE: Nagasaki University's Ac Title Effect of Higher Financial Leverage Bangladesh Author(s) 内田, 滋 Citation 長崎大学東南アジア研究年報. vol.45, p.13-20; 200 Issue 2004-03-25 Date URL http://hdl.handle.net/10069/6786
More informationLOGISTIC REGRESSION ANALYSIS IN PERSONAL LOAN BANKRUPTCY. Siti Mursyida Abdul Karim & Dr. Haliza Abdul Rahman
LOGISTIC REGRESSION ANALYSIS IN PERSONAL LOAN BANKRUPTCY Abstract Siti Mursyida Abdul Karim & Dr. Haliza Abdul Rahman Personal loan bankruptcy is defined as a person who had been declared as a bankrupt
More information9. Logit and Probit Models For Dichotomous Data
Sociology 740 John Fox Lecture Notes 9. Logit and Probit Models For Dichotomous Data Copyright 2014 by John Fox Logit and Probit Models for Dichotomous Responses 1 1. Goals: I To show how models similar
More informationReview questions for Multinomial Logit/Probit, Tobit, Heckit, Quantile Regressions
1. I estimated a multinomial logit model of employment behavior using data from the 2006 Current Population Survey. The three possible outcomes for a person are employed (outcome=1), unemployed (outcome=2)
More informationKeywords Akiake Information criterion, Automobile, Bonus-Malus, Exponential family, Linear regression, Residuals, Scaled deviance. I.
Application of the Generalized Linear Models in Actuarial Framework BY MURWAN H. M. A. SIDDIG School of Mathematics, Faculty of Engineering Physical Science, The University of Manchester, Oxford Road,
More informationOverdraft Frequency and Payday Borrowing An analysis of characteristics associated with overdrafters
A brief from Feb 2015 Overdraft Frequency and Payday Borrowing An analysis of characteristics associated with overdrafters Overview According to an analysis of banks account data published by the Consumer
More informationWest Coast Stata Users Group Meeting, October 25, 2007
Estimating Heterogeneous Choice Models with Stata Richard Williams, Notre Dame Sociology, rwilliam@nd.edu oglm support page: http://www.nd.edu/~rwilliam/oglm/index.html West Coast Stata Users Group Meeting,
More informationImpact of Weekdays on the Return Rate of Stock Price Index: Evidence from the Stock Exchange of Thailand
Journal of Finance and Accounting 2018; 6(1): 35-41 http://www.sciencepublishinggroup.com/j/jfa doi: 10.11648/j.jfa.20180601.15 ISSN: 2330-7331 (Print); ISSN: 2330-7323 (Online) Impact of Weekdays on the
More informationFinancial Literacy and Financial Behavior among Young Adults: Evidence and Implications
Numeracy Advancing Education in Quantitative Literacy Volume 6 Issue 2 Article 5 7-1-2013 Financial Literacy and Financial Behavior among Young Adults: Evidence and Implications Carlo de Bassa Scheresberg
More informationWage Determinants Analysis by Quantile Regression Tree
Communications of the Korean Statistical Society 2012, Vol. 19, No. 2, 293 301 DOI: http://dx.doi.org/10.5351/ckss.2012.19.2.293 Wage Determinants Analysis by Quantile Regression Tree Youngjae Chang 1,a
More informationMODELLING HEALTH MAINTENANCE ORGANIZATIONS PAYMENTS UNDER THE NATIONAL HEALTH INSURANCE SCHEME IN NIGERIA
MODELLING HEALTH MAINTENANCE ORGANIZATIONS PAYMENTS UNDER THE NATIONAL HEALTH INSURANCE SCHEME IN NIGERIA *Akinyemi M.I 1, Adeleke I. 2, Adedoyin C. 3 1 Department of Mathematics, University of Lagos,
More informationLecture 21: Logit Models for Multinomial Responses Continued
Lecture 21: Logit Models for Multinomial Responses Continued Dipankar Bandyopadhyay, Ph.D. BMTRY 711: Analysis of Categorical Data Spring 2011 Division of Biostatistics and Epidemiology Medical University
More informationThe Capital Accumulation Ratio as an Indicator of Retirement Adequacy
The Capital Accumulation Ratio as an Indicator of Retirement Adequacy Rui Yao 1, Sherman D. Hanna 2, and Catherine P. Montalto 3 The relationship between meeting the Capital Accumulation Ratio Guideline
More informationThe B.E. Journal of Economic Analysis & Policy
The B.E. Journal of Economic Analysis & Policy T o p i c s V o l u m e 11, Issue 3 2011 Article 8 SOCIOECONOMIC ST A T U S AND HEALTH ACROSS GENERATIONS AND OVER THE LIFE COURSE Occupational Status and
More informationTo be two or not be two, that is a LOGISTIC question
MWSUG 2016 - Paper AA18 To be two or not be two, that is a LOGISTIC question Robert G. Downer, Grand Valley State University, Allendale, MI ABSTRACT A binary response is very common in logistic regression
More informationAppendix A: Detailed Methodology and Statistical Methods
Appendix A: Detailed Methodology and Statistical Methods I. Detailed Methodology Research Design AARP s 2003 multicultural project focuses on volunteerism and charitable giving. One broad goal of the project
More informationCalculating the Probabilities of Member Engagement
Calculating the Probabilities of Member Engagement by Larry J. Seibert, Ph.D. Binary logistic regression is a regression technique that is used to calculate the probability of an outcome when there are
More informationResearch on the Influencing Factors of Personal Credit Based on a Risk Management Model in the Background of Big Data
Journal of Applied Mathematics and Physics, 207, 5, 722-733 http://www.scirp.org/journal/jamp ISSN Online: 2327-4379 ISSN Print: 2327-4352 Research on the Influencing Factors of Personal Credit Based on
More informationMemorandum. Human Resources Division
Memorandum Human Resources Division TO: FROM: RE: Vacellia Clark, Chief Examiner Civil Service Commission Human Resources Staff Establish a Passing Score for Animal Control Officer DATE: October 30, 2013
More informationa. Explain why the coefficients change in the observed direction when switching from OLS to Tobit estimation.
1. Using data from IRS Form 5500 filings by U.S. pension plans, I estimated a model of contributions to pension plans as ln(1 + c i ) = α 0 + U i α 1 + PD i α 2 + e i Where the subscript i indicates the
More informationInternational journal of advanced production and industrial engineering (A Blind Peer Reviewed Journal)
IJAPIE-2016-10-406, Vol 1(4), 40-44 International journal of advanced production and industrial engineering (A Blind Peer Reviewed Journal) Consumption and Market Beta: Empirical Evidence from India Nand
More informationAssessment on Credit Risk of Real Estate Based on Logistic Regression Model
Assessment on Credit Risk of Real Estate Based on Logistic Regression Model Li Hongli 1, a, Song Liwei 2,b 1 Chongqing Engineering Polytechnic College, Chongqing400037, China 2 Division of Planning and
More informationChallenges and Opportunities with NCHS Linked Data Files
Challenges and Opportunities with NCHS Linked Data Files Council of Professional Associations on Federal Statistics (COPAFS) Provides government policy decision makers with information that demonstrates
More informationPolicy Brief. protection?} Do the insured have adequate. The Impact of Health Reform on Underinsurance in Massachusetts:
protection?} The Impact of Health Reform on Underinsurance in Massachusetts: Do the insured have adequate Reform Policy Brief Massachusetts Health Reform Survey Policy Brief {PREPARED BY} Sharon K. Long
More informationThe Effect of Household Structure, Social Support, Neighborhood and Policy Context on Financial Strain: Evidence from the Hispanic EPESE
The Effect of Household Structure, Social Support, Neighborhood and Policy Context on Financial Strain: Evidence from the Hispanic EPESE Background. Recent evidence confirms that Hispanic life expectancy
More informationCHAPTER 11 Regression with a Binary Dependent Variable. Kazu Matsuda IBEC PHBU 430 Econometrics
CHAPTER 11 Regression with a Binary Dependent Variable Kazu Matsuda IBEC PHBU 430 Econometrics Mortgage Application Example Two people, identical but for their race, walk into a bank and apply for a mortgage,
More informationMondays from 6p to 8p in Nitze Building N417. Wednesdays from 8a to 9a in BOB 718
Basic logistics Class Mondays from 6p to 8p in Nitze Building N417 Office hours Wednesdays from 8a to 9a in BOB 718 My Contact Info nhiggins@jhu.edu Course website http://www.nathanielhiggins.com (Not
More informationSupporting Information
Supporting Information Israel et al. 10.1073/pnas.1409794111 SI Text Dunedin Study Sample. Participants are members of the Dunedin Multidisciplinary Health and Development Study, a longitudinal investigation
More informationMoral hazard in a voluntary deposit insurance system: Revisited
MPRA Munich Personal RePEc Archive Moral hazard in a voluntary deposit insurance system: Revisited Pablo Camacho-Gutiérrez and Vanessa M. González-Cantú 31. May 2007 Online at http://mpra.ub.uni-muenchen.de/3909/
More informationCategorical and Limited Dependent Variables
Categorical and Limited Dependent Variables Public Affairs 56:824:708:01 Public Administration 56:834:652:01 Fall Semester 2015, BSB 108, Tuesdays 6-8:40pm August 31, 2015 Paul A. Jargowsky, Ph.D. 856-225-2729;
More informationMarried Women s Labor Supply Decision and Husband s Work Status: The Experience of Taiwan
Married Women s Labor Supply Decision and Husband s Work Status: The Experience of Taiwan Hwei-Lin Chuang* Professor Department of Economics National Tsing Hua University Hsin Chu, Taiwan 300 Tel: 886-3-5742892
More informationImpact of Household Income on Poverty Levels
Impact of Household Income on Poverty Levels ECON 3161 Econometrics, Fall 2015 Prof. Shatakshee Dhongde Group 8 Annie Strothmann Anne Marsh Samuel Brown Abstract: The relationship between poverty and household
More informationPersonality Traits and Economic Preparation for Retirement
Personality Traits and Economic Preparation for Retirement Michael D. Hurd Susann Rohwedder RAND Angela Lee Duckworth University of Pennsylvania and David R. Weir University of Michigan 14 th Annual Joint
More informationRenters Report Future Home Buying Optimism, While Family Financial Assistance Is Most Available to Populations with Higher Homeownership Rates
Renters Report Future Home Buying Optimism, While Family Financial Assistance Is Most Available to Populations with Higher Homeownership Rates National Housing Survey Topic Analysis Q3 2016 Published on
More informationFinal Exam, section 1. Thursday, May hour, 30 minutes
San Francisco State University Michael Bar ECON 312 Spring 2018 Final Exam, section 1 Thursday, May 17 1 hour, 30 minutes Name: Instructions 1. This is closed book, closed notes exam. 2. You can use one
More informationAnalysis of the Delaware Market. For Organically Grown Produce*
Analysis of the Delaware Market For Organically Grown Produce* by Andrew J, Groff Undergraduate Research Assistant Delaware Agricultural Experiment Station Department of Food and Resource Economics University
More informationHealth Expenditures and Life Expectancy Around the World: a Quantile Regression Approach
` DISCUSSION PAPER SERIES Health Expenditures and Life Expectancy Around the World: a Quantile Regression Approach Maksym Obrizan Kyiv School of Economics and Kyiv Economics Institute George L. Wehby University
More informationEstimating Ordered Categorical Variables Using Panel Data: A Generalised Ordered Probit Model with an Autofit Procedure
Journal of Economics and Econometrics Vol. 54, No.1, 2011 pp. 7-23 ISSN 2032-9652 E-ISSN 2032-9660 Estimating Ordered Categorical Variables Using Panel Data: A Generalised Ordered Probit Model with an
More informationQuestions and Answers about Phased Retirement: A Sloan Work and Family Research Network Fact Sheet
Questions and Answers about Phased Retirement: A Sloan Work and Family Research Network Fact Sheet Introduction The Sloan Work and Family Research Network has prepared Fact Sheets that provide statistical
More informationWhy do the youth in Jamaica neither study nor work? Evidence from JSLC 2001
VERY PRELIMINARY, PLEASE DO NOT QUOTE Why do the youth in Jamaica neither study nor work? Evidence from JSLC 2001 Abstract Abbi Kedir 1 University of Leicester, UK E-mail: ak138@le.ac.uk and Michael Henry
More informationYour Name (Please print) Did you agree to take the optional portion of the final exam Yes No. Directions
Your Name (Please print) Did you agree to take the optional portion of the final exam Yes No (Your online answer will be used to verify your response.) Directions There are two parts to the final exam.
More informationThe model is estimated including a fixed effect for each family (u i ). The estimated model was:
1. In a 1996 article, Mark Wilhelm examined whether parents bequests are altruistic. 1 According to the altruistic model of bequests, a parent with several children would leave larger bequests to children
More informationHedging Longevity Risk using Longevity Swaps: A Case Study of the Social Security and National Insurance Trust (SSNIT), Ghana
International Journal of Finance and Accounting 2016, 5(4): 165-170 DOI: 10.5923/j.ijfa.20160504.01 Hedging Longevity Risk using Longevity Swaps: A Case Study of the Social Security and National Insurance
More informationDYNAMICS OF URBAN INFORMAL
DYNAMICS OF URBAN INFORMAL EMPLOYMENT IN BANGLADESH Selim Raihan Professor of Economics, University of Dhaka and Executive Director, SANEM ICRIER Conference on Creating Jobs in South Asia 3-4 December
More informationHOUSEHOLDS INDEBTEDNESS: A MICROECONOMIC ANALYSIS BASED ON THE RESULTS OF THE HOUSEHOLDS FINANCIAL AND CONSUMPTION SURVEY*
HOUSEHOLDS INDEBTEDNESS: A MICROECONOMIC ANALYSIS BASED ON THE RESULTS OF THE HOUSEHOLDS FINANCIAL AND CONSUMPTION SURVEY* Sónia Costa** Luísa Farinha** 133 Abstract The analysis of the Portuguese households
More informationDemographic and Economic Characteristics of Children in Families Receiving Social Security
Each month, over 3 million children receive benefits from Social Security, accounting for one of every seven Social Security beneficiaries. This article examines the demographic characteristics and economic
More informationIndividual income, income distribution, and self rated health in Japan: cross sectional analysis of nationally representative sample. proposed.
Individual income, income distribution, and self rated health in Japan: cross sectional analysis of nationally representative sample Kenji Shibuya, Hideki Hashimoto, Eiji Yano Abstract Objective To assess
More informationAllison notes there are two conditions for using fixed effects methods.
Panel Data 3: Conditional Logit/ Fixed Effects Logit Models Richard Williams, University of Notre Dame, http://www3.nd.edu/~rwilliam/ Last revised April 2, 2017 These notes borrow very heavily, sometimes
More informationLabor Participation and Gender Inequality in Indonesia. Preliminary Draft DO NOT QUOTE
Labor Participation and Gender Inequality in Indonesia Preliminary Draft DO NOT QUOTE I. Introduction Income disparities between males and females have been identified as one major issue in the process
More informationMANUEL C. F. PONTES, NANCY M. H. PONTES, and PHILLIP A. LEWIS
Health Insurance Sources for Nonelderly Patient Visits to Physician Offices, Hospital Outpatient Departments, and Emergency Departments in the United States MANUEL C. F. PONTES, NANCY M. H. PONTES, and
More information401(k) PLANS AND RACE
November 2009, Number 9-24 401(k) PLANS AND RACE By Alicia H. Munnell and Christopher Sullivan* Introduction Many data sources show a disparity among racial and ethnic groups regarding participation in
More informationA Comparison of Univariate Probit and Logit. Models Using Simulation
Applied Mathematical Sciences, Vol. 12, 2018, no. 4, 185-204 HIKARI Ltd, www.m-hikari.com https://doi.org/10.12988/ams.2018.818 A Comparison of Univariate Probit and Logit Models Using Simulation Abeer
More informationLogistics Regression & Industry Modeling
Logistics Regression & Industry Modeling Framing Financial Problems as Probabilities Russ Koesterich, CFA Chief North American Strategist Logistics Regression & Probability So far as the laws of mathematics
More informationWillingness to Pay for Green Electricity in Tianjin, China: Based on Contingent Valuation Method
Willingness to Pay for Green Electricity in Tianjin, China: Based on Contingent Valuation Method Li-Qiu Liu College of Management and Economics, Tianjin University the 40 th June 20, 2017, IAEE, Singapore
More informationOrdinal Multinomial Logistic Regression. Thom M. Suhy Southern Methodist University May14th, 2013
Ordinal Multinomial Logistic Thom M. Suhy Southern Methodist University May14th, 2013 GLM Generalized Linear Model (GLM) Framework for statistical analysis (Gelman and Hill, 2007, p. 135) Linear Continuous
More informationEffect of Education on Wage Earning
Effect of Education on Wage Earning Group Members: Quentin Talley, Thomas Wang, Geoff Zaski Abstract The scope of this project includes individuals aged 18-65 who finished their education and do not have
More informationILLINOIS EPA INITIATIVE: ILLINOIS LEAKING UNDERGROUND STORAGE TANK PROGRAM CLOSURE AND PROPERTY REUSE STUDY. Hernando Albarracin Meagan Musgrave
ILLINOIS EPA INITIATIVE: ILLINOIS LEAKING UNDERGROUND STORAGE TANK PROGRAM CLOSURE AND PROPERTY REUSE STUDY Hernando Albarracin Meagan Musgrave BACKGROUND 1998 Illinois General Assembly created Illinois
More informationDEMOGRAPHICS OF PAYDAY LENDING IN OKLAHOMA
October 2014 DEMOGRAPHICS OF PAYDAY LENDING IN OKLAHOMA Report Prepared for the Oklahoma Assets Network by Haydar Kurban Adji Fatou Diagne 0 This report was prepared for the Oklahoma Assets Network by
More informationEffect of Health Expenditure on GDP, a Panel Study Based on Pakistan, China, India and Bangladesh
International Journal of Health Economics and Policy 2017; 2(2): 57-62 http://www.sciencepublishinggroup.com/j/hep doi: 10.11648/j.hep.20170202.13 Effect of Health Expenditure on GDP, a Panel Study Based
More informationHow exogenous is exogenous income? A longitudinal study of lottery winners in the UK
How exogenous is exogenous income? A longitudinal study of lottery winners in the UK Dita Eckardt London School of Economics Nattavudh Powdthavee CEP, London School of Economics and MIASER, University
More informationIJBARR E- ISSN X ISSN ROLE OF PLANNING IN THE FINANCIAL DECISION MAKING OF INDIVIDUALS
ROLE OF PLANNING IN THE FINANCIAL DECISION MAKING OF INDIVIDUALS Dr.P.Maheswari Associate Professor, Kasturba Gandhi College for Women, West Marredpally, Secunderabad, India. INTRODUCTION The globalization
More informationA Study On Policyholders Satisfaction On Service Of LIC: Reference To Coimbatore District
Research Paper Volume 2 Issue 10 June 2015 International Journal of Informative & Futuristic Research ISSN (Online): 2347-1697 A Study On Policyholders Satisfaction On Service Of LIC: Reference To Coimbatore
More informationHow Do Faculty and Staff Select between Defined Benefit and Defined Contribution Retirement Plans?
Trends and Issues July 2018 How Do Faculty and Staff Select between Defined Benefit and Defined Contribution Retirement Plans? Robert K. Toutkoushian, University of Georgia Paula Sanford, University of
More informationThe Influence of Demographic Factors on the Investment Objectives of Retail Investors in the Nigerian Capital Market
The Influence of Demographic Factors on the Investment Objectives of Retail Investors in the Nigerian Capital Market Nneka Rosemary Ikeobi * Peter E. Arinze 2. Department of Actuarial Science, Faculty
More informationData Appendix. A.1. The 2007 survey
Data Appendix A.1. The 2007 survey The survey data used draw on a sample of Italian clients of a large Italian bank. The survey was conducted between June and September 2007 and elicited detailed financial
More informationInterviewer-Respondent Socio-Demographic Matching and Survey Cooperation
Vol. 3, Issue 4, 2010 Interviewer-Respondent Socio-Demographic Matching and Survey Cooperation Oliver Lipps Survey Practice 10.29115/SP-2010-0019 Aug 01, 2010 Tags: survey practice Abstract Interviewer-Respondent
More informationRace to Employment: Does Race affect the probability of Employment?
Senior Project Department of Economics Race to Employment: Does Race affect the probability of Employment? Corey Holland May 2013 Advisors: Francesco Renna Abstract This paper estimates the correlation
More informationInternet Appendix. The survey data relies on a sample of Italian clients of a large Italian bank. The survey,
Internet Appendix A1. The 2007 survey The survey data relies on a sample of Italian clients of a large Italian bank. The survey, conducted between June and September 2007, provides detailed financial and
More informationNBER WORKING PAPER SERIES OCCUPATIONAL STATUS AND HEALTH TRANSITIONS. G. Brant Morefield David C. Ribar Christopher J. Ruhm
NBER WORKING PAPER SERIES OCCUPATIONAL STATUS AND HEALTH TRANSITIONS G. Brant Morefield David C. Ribar Christopher J. Ruhm Working Paper 16794 http://www.nber.org/papers/w16794 NATIONAL BUREAU OF ECONOMIC
More informationEffect of Financial Resources And Credit On Savings Behavior Of Low-Income Families
Effect of Financial Resources And Credit On Savings Behavior Of Low-Income Families Joan Koonce Lewis, 1 University of Georgia This study examined the effects of available financial resources, credit use,
More informationStructure and Dynamics of Labour Market in Bangladesh
A SEMINAR PAPER ON Structure and Dynamics of Labour Market in Bangladesh Course title: Seminar Course code: AEC 598 Summer, 2018 SUBMITTED TO Course Instructors 1.Dr. Mizanur Rahman Professor BSMRAU, Gazipur
More informationFinancial Literacy and Subjective Expectations Questions: A Validation Exercise
Financial Literacy and Subjective Expectations Questions: A Validation Exercise Monica Paiella University of Naples Parthenope Dept. of Business and Economic Studies (Room 314) Via General Parisi 13, 80133
More information